arXiv 5 Sep 2023 · Econometrics · 1 citations (OpenAlex)
arXiv:2309.02089 · PDF · DOI · OpenAlex · Extracted main text
Even though dyadic regressions are widely used in empirical applications, the (asymptotic) properties of estimation methods only began to be studied recently in the literature. This paper aims to provide in a step-by-step manner how U-statistics tools can be applied to obtain the asymptotic properties of pairwise differences estimators for a two-way fixed effects model of dyadic interactions. More specifically, we first propose an estimator for the model that relies on pairwise differencing such that the fixed effects are differenced out. As a result, the summands of the influence function will not be independent anymore, showing dependence on the individual level and translating to the fact that the usual law of large numbers and central limit theorems do not straightforwardly apply. To overcome such obstacles, we show how to generalize tools of U-statistics for single-index variables to the double-indices context of dyadic datasets. A key result is that there can be different ways of defining the Hajek projection for a directed dyadic structure, which will lead to distinct, but equivalent, consistent estimators for the asymptotic variances. The results presented in this paper are easily extended to non-linear models.
appendix boundary found by appendix_command · 58% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Jochmans, K (2018) Semiparametric analysis of network formation | 1.000 | 11 | 5 | 100% |
| 2 | Serfling, R. J (2009) Approximation theorems of mathematical statistics | 1.000 | 10 | 3 | 100% |
| 3 | Charbonneau, K. B (2017) Multiple fixed effects in binary response panel data models | 1.000 | 9 | 4 | 100% |
| 4 | Graham, B. S (2019) Network data, Tech | 0.928 | 4 | 3 | 100% |
| 5 | Graham, B. S (2017) An econometric model of network formation with degree heterogeneity | 0.909 | 12 | 6 | 75% |
| 6 | Fernández-Val, I. and M. Weidner (2016) Individual and time effects in nonlinear panel models with large N, T | 0.811 | 4 | 2 | 100% |
| 7 | Graham, B. S (2020) Dyadic regression, in | 0.811 | 4 | 2 | 100% |
| 8 | Hoeffding, W., H. Robbins, et al (1948) The central limit theorem for dependent random variables | 0.737 | 4 | 4 | 50% |
| 9 | Jochmans, K (2017) Two-way models for gravity | 0.644 | 2 | 2 | 100% |
| 10 | Anderson, J. E. and E. Van Wincoop (2003) Gravity with gravitas: A solution to the border puzzle | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 22 scored citations.